This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We are seeking a highly skilled and experienced Senior Software Engineer with strong experience in designing, configuring, and building agentic AI systems, cloud-native software applications, and ML-enabled solutions. In this role, you will develop scalable software systems that leverage large language models, intelligent agents, workflow orchestration, APIs, cloud services, and MLOps practices. The ideal candidate combines strong software engineering fundamentals with practical experience in AI/ML systems, including agent frameworks, retrieval-augmented generation, model integration, evaluation, deployment, monitoring, and automation. You will work closely with product teams, data scientists, ML engineers, platform teams, and business stakeholders to deliver secure, reliable, and maintainable AI-enabled software solutions.
Job Responsibility
Design, configure, and build agentic AI systems that can reason, plan, use tools, execute workflows, and interact with enterprise systems
Develop scalable software applications and services using modern cloud-native architectures
Integrate large language models, APIs, databases, vector stores, and orchestration frameworks into production-ready applications
Build and maintain AI-enabled workflows using agent frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or similar technologies
Implement retrieval-augmented generation patterns, including document ingestion, chunking, embedding generation, vector search, reranking, and response generation
Partner with data science and ML teams to operationalize machine learning models and AI capabilities into software products
Apply MLOps practices for model deployment, monitoring, versioning, evaluation, governance, and continuous improvement
Develop reusable components, APIs, services, and integration patterns to accelerate AI solution delivery
Define and implement robust cloud architectures, preferably on AWS, using serverless, containerized, or microservices-based approaches
Implement observability, logging, monitoring, error handling, and performance optimization for AI and ML-enabled applications
Evaluate and improve agent performance, including prompt quality, tool selection, response accuracy, latency, cost, and reliability
Requirements
Strong hands-on software engineering experience with Python, JavaScript/TypeScript, SQL/NoSQL, APIs, and cloud-native application development
Experience building or integrating applications with generative AI, LLMs, agentic workflows, RAG patterns, or AI orchestration frameworks
Working knowledge of ML lifecycle concepts, including model deployment, evaluation, monitoring, versioning, and automation
Experience with CI/CD, testing, containerization, observability, and production-grade software delivery
Strong problem-solving, communication, collaboration, and technical ownership skills
Nice to have
Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or similar agent frameworks
Experience with vector databases, embeddings, semantic search, reranking, prompt engineering, fine-tuning, or LLM evaluation
Experience with MLOps tools such as MLflow, SageMaker, Databricks, Kubeflow, Airflow, or similar platforms
Familiarity with serverless, microservices, event-driven architecture, Kubernetes, or managed cloud AI/ML services
Knowledge of responsible AI, model governance, human-in-the-loop workflows, security, privacy, and regulated environments